Erweiterte Suche | Seiten im Überblick

NLP in Industry: challenges and best practices

Module Description

Lecturer	Daniel Dahlmeier
Module Type	Proseminar / Hauptseminar
Language	English
First Session	25.04.2025
Time and Place	Friday, 08:15–09:45, online
Commitment Period	tbd.

Participants

All advanced Bachelor students and all Master students. Students from MSc Data and Computer Science or MSc Scientific Computing with Anwendungsgebiet Computational Linguistics are welcome after getting permission from the lecturer.

Prerequisite for Participation

• Mathematical Foundations of CL (or a comparable introductory class to linear algebra and theory of probability)
• Statistical Methods for CL (or a comparable introductory class to machine learning)

Assessment

• Regular and active attendance of seminar (40%)
• Independent study of assigned scientific papers, clarity of report and presentation (60%)

Content

This seminar explores the challenges and best practices for natural language processing (NLP) in industry with a focus on deep learning and large language models (LLMs).

The course will focus on practical topics, including data engineering, prompt engineering, AI architecture, finetuning, model deployment, evaluation, and real-world considerations, such as legal/data protection, viable business cases, and ethical implications.

Students will engage with key concepts from the textbooks Designing Machine Learning Systems and AI Engineering by Chip Huyen and will be presenting selected chapters in class. Each student will present a selected topic and submit a written report. Additionally, participants will implement a course project to gain practical insights into building modern LLM systems.

For questions about the seminar, please email x0unj76@uni-heidelberg.de.

Module Overview

Agenda

Date

Session

Materials

Literature

• AI Engineering. Chip Huyen. 2025.
• Designing Machine Learning Systems. Chip Huyen. 2022.

» More Materials